In francojc/tadr: Text as Data Resources

library(tidyverse)

Curate data

Rate My Professor sample dataset

rmp <- read_csv(file = "data/original/rate_my_professor_sample/RateMyProfessor_Sample data.csv")

rmp_curated <- 
  rmp %>% 
  select(online = IsCourseOnline, student_star, comments) %>% 
  filter(student_star == 1 | student_star == 5) %>% 
  mutate(id = row_number()) %>% 
  group_by(online) %>% 
  slice_sample(n = 5) %>% 
  ungroup() %>% 
  select(rating_id = id, online, student_star, comments)

fs::dir_create(path = "data/derived/rate_my_professor_sample/")
write_csv(rmp_curated, file = "data/derived/rate_my_professor_sample/rmp_curated.csv")

data_dic_starter <- function(data, file_path) {
  # Function:
  # Creates a .csv file with the basic information
  # to document a curated dataset

  tibble(variable_name = names(data), # column with existing variable names
         name = "", # column for human-readable names
         description = "") %>% # column for prose description
    write_csv(file = file_path) # write to disk
}

data_dic_starter(rmp_curated, file_path = "data/derived/rate_my_professor_sample/rmp_curated_data_dictionary.csv")

francojc/tadr documentation built on April 26, 2022, 7:55 p.m.